Multivariable Models Based on Baseline Imaging Features and Clinicopathological Characteristics to Predict Breast Pathologic Response after Neoadjuvant Chemotherapy in Patients with Breast Cancer

Breast Care ◽  
2021 ◽  
Author(s):  
Peixian Chen ◽  
Chuan Wang ◽  
Ruiliang Lu ◽  
Ruilin Pan ◽  
Lewei Zhu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neoadjuvant Chemotherapy ◽  
Prediction Models ◽  
Univariate Analysis ◽  
Pathologic Complete Response ◽  
Clinicopathological Characteristics ◽  
Her2 Status ◽  
Imaging Features ◽  
Multivariate Models ◽  
Multivariable Models

Abstract Introduction Currently, the accurate evaluation and prediction of response to neoadjuvant chemotherapy (NAC) remains a great challenge. We developed several multivariate models based on baseline imaging features and clinicopathological characteristics to predict the breast pathologic complete response (pCR). Methods We retrospectively collected clinicopathological and imaging data of patients who received NAC and subsequent surgery for breast cancer at our hospital from 2014 June till 2020 September. We used mammography, ultrasound and magnetic resonance imaging (MRI) to investigate the breast tumors at baseline. Results A total of 308 patients were included and 111 patients achieved pCR. The HER2 status and Ki-67 index were significant factors for pCR on univariate analysis and in all multivariate models. Among the prediction models in this study, the ultrasound-MRI model performed the best, producing an area under curve of 0.801 (95%CI=0.749-0.852), a sensitivity of 0.797 and a specificity of 0.676. Conclusion Among the multivariable models constructed in this study, the ultrasound plus MRI model performed the best in predicting the probability of pCR after NAC. Further validation is required before it is generalized.

Does biologic subtype and pathologic response after neoadjuvant chemotherapy predict locoregional recurrence?

2014 ◽  
Vol 32 (26_suppl) ◽  
pp. 65-65
Author(s):  
T. Jonathan Yang ◽  
Monica Morrow ◽  
Shanu Modi ◽  
Kate Krause ◽  
Chun Siu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neoadjuvant Chemotherapy ◽  
Locoregional Recurrence ◽  
Cox Regression ◽  
Breast Cancer Subtype ◽  
Univariate Analysis ◽  
Pathologic Complete Response ◽  
High Risk Population ◽  
Cox Regression Analysis ◽  
Her2 Breast Cancer

65 Background: The relative contribution of biological subtype and response to neoadjuvant chemotherapy (NAC) to locoregional recurrence (LRR) is uncertain. We aim to determine if these factors identify a high risk population for LRR. Methods: 233 patients received anthracycline/taxane-based NAC, mastectomy and postmastectomy radiation therapy (PMRT) in 2000-2009 for Stage II-III breast cancer. 53% (n=123) were HR+ (ER or PR+/HER2-), 23% (53) HER2+ (HER2+/HR+ or HR-), and 24% (57) TN (HR-/HER2-). 76% of HER2+ received trastuzumab. Median PMRT dose was 50 Gy to chest wall and regional nodes. Pathologic complete response (pCR) rates were compared using Fisher's exact test. Rates of LRR and distant recurrence (DR) were estimated by Kaplan-Meier methods. Cox regression analysis was performed. Results: Median follow-up was 62 months (range 7-161) with 21 LRR, 84 DR and 58 deaths. pCR rate and 5-year LRR rates were 14% and 7% in the entire cohort, respectively. Significantly more TN and HER2+ patients achieved pCR than HR+ patients (Table 1, p=0.003). TN patients had higher 5-year LRR rate compared to HR+ and HER2+ patients (18% vs. 4% and 6%, p=0.02). The 5-year LRR rate was 0% in pCR patients versus 9% in non-pCR patients (p=0.06). In patients without pCR, TN subtype was associated with increased LRR (23% at 5-year vs. 4% HR+ and 7% HER2+; p=0.001). TN patients without pCR were also associated with increased DR (48% at 5-year vs. 29% HR+ and 30% HER2+, p=0.02). On univariate analysis, TN subtype (HR=2.0, p=0.008), pathologic stage (HR=2.2, p=0.02), and pN+ status (HR=9.3, p=0.03) were associated with increased LRR. Conclusions: Although response to NAC strongly correlates with breast cancer subtype, patients with HR+ and HER2+ breast cancer had favorable rates of LRR regardless of response to NAC, perhaps because of additional postoperative targeted therapy. In contrast, while no LRR was seen in TN patients with pCR, those with poor response to NAC had significantly higher LRR risk, underscoring the need for potential new treatment strategies to improve local control in this population. [Table: see text]

Prediction of Pathologic Complete Response to Neoadjuvant Chemotherapy Using Machine Learning Models in Patients with Breast Cancer

2021 ◽  
Author(s):  
Ji-Yeon Kim ◽  
Eunjoo Jeon ◽  
Soonhwan Kwon ◽  
Hyungsik Jung ◽  
Sunghoon Joo ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Neoadjuvant Chemotherapy ◽  
Prediction Model ◽  
Prediction Models ◽  
Locally Advanced ◽  
Pathologic Complete Response ◽  
Complete Response ◽  
Bayesian Optimization ◽  
Pathological Characteristics

Abstract BackgroundThe aim of this study was to develop a machine learning(ML) based model to accurately predict pathologic complete response(pCR) to neoadjuvant chemotherapy(NAC) using pretreatment clinical and pathological characteristics of electronic medical record(EMR) data in breast cancer(BC).Methods The EMR data from patients diagnosed with early and locally advanced BC and who received NAC followed by curative surgery were reviewed. A total of 16 clinical and pathological characteristics was selected to develop ML model. We practiced six ML models using default settings for multivariate analysis with extracted variables. ResultsIn total, 2,065 patients were included in this analysis. Overall, 30.6% (n=632) of patients achieved pCR. Among six ML models, the LightGBM had the highest area under the curve (AUC) for pCR prediction. After hyper-parameter tuning with Bayesian optimization, AUC was 0.810. Performance of pCR prediction models in different histology-based subtypes was compared. The AUC was highest in HR+HER2- subgroup and lowest in HR-/HER2- subgroup (HR+/HER2- 0.841, HR+/HER2+ 0.716, HR-/HER2 0.753, HR-/HER2- 0.653).ConclusionsA ML based pCR prediction model using pre-treatment clinical and pathological characteristics provided useful information to predict pCR during NAC. This prediction model would help to determine treatment strategy in patients with BC planned NAC.

scholarly journals Linc00665 Can Predict the Response to Cisplatin-Paclitaxel Neoadjuvant Chemotherapy for Breast Cancer Patients

2021 ◽  
Vol 11 ◽  
Author(s):  
Huijuan Dai ◽  
Xiaonan Sheng ◽  
Rui Sha ◽  
Jing Peng ◽  
Fan Yang ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neoadjuvant Chemotherapy ◽  
Cancer Patients ◽  
Univariate Analysis ◽  
Enrichment Analysis ◽  
Predictive Biomarker ◽  
Gene Set Enrichment Analysis ◽  
Her2 Status ◽  
Breast Cancer Patients ◽  
Kegg Analysis

ObjectiveLinc00665 is a novel long non-coding RNA that can promote the progression of breast cancer, but its value in predicting the efficacy of neoadjuvant chemotherapy (NAC) for breast cancer has not been reported. We aim to analyze the correlation between Linc00665 expression and pathological complete response (pCR) in breast cancer patients.Materials and MethodsThe present study examined the predictive role of Linc00665 expression in pCR after NAC using both univariate and multivariate logistic regression analyses. Receiver operating characteristic (ROC) curve and area under curve (AUC) were utilized to evaluate the performance of Linc00665 in predicting pCR. The Kyoto Encyclopedia of Gene and Genome (KEGG) analysis and Gene Set Enrichment Analysis (GSEA) were also conducted to determine the biological processes where Linc00665 may participate in.ResultsThe present study study totally enrolled 102 breast cancer patients. The univariate analysis showed that Linc00665 level, human epidermal growth factor receptor 2 (HER2) status and hormone receptor (HR) status were correlated with pCR. The multivariate analysis showed that Linc00665 expression was an independent predictor of pCR (OR = 0.351, 95% CI: 0.125–0.936, P = 0.040), especially in patients with HR-positive/HER2-negative subtype (OR = 0.272, 95% CI: 0.104–0.664, P = 0.005). The KEGG analysis indicated that Linc00665 may be involved in drug metabolism. The GSEA analysis revealed that Linc00665 is correlated to DNA damage repair.ConclusionLinc00665 may be a potential novel predictive biomarker for breast cancer in NAC, especially for HR-positive/HER2-negative patients.

Role of proliferation in response to neoadjuvant chemotherapy in GEICAM/2006-03 and GEICAM/2006-14 breast cancer patients.

2012 ◽  
Vol 30 (15_suppl) ◽  
pp. 10616-10616
Author(s):  
E. Alba ◽  
Joan Albanell ◽  
Jose Ignacio Chacon Lopez-Muniz ◽  
Lourdes Calvo ◽  
Juan De la Haba- Rodriguez ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Logistic Regression ◽  
Neoadjuvant Chemotherapy ◽  
Predictive Factor ◽  
Ductal Carcinoma ◽  
Histological Grade ◽  
Univariate Analysis ◽  
Her2 Status ◽  
Multivariate Logistic Regression ◽  
Long Term Outcome

10616 Background: Ki67 proliferation biomarker determined by immunohistochemistry (IHC) has been studied as a prognostic and predictive factor in Operable Breast Cancer (OBC). Ki67 modifications after neoadjuvant endocrine therapy have been correlated with long term outcome. However, there is no robust data about its predictive role in Neoadjuvant Chemotherapy (NC). In this study, we investigated Ki67 value as predictor of NC efficacy. Methods: 193 patients (pts) from 2 GEICAM phase II randomized trials (2006-03 and 2006-14) were included: 78 (40%) received epirubicine plus cyclophosphamide followed by docetaxel (EC-D), 41 (21%) EC-D plus carboplatin, and out of the 74 HER2+ pts, 37 (19%) received EC-D plus tratuzumab and 37 (19%) EC-D plus lapatinib. Median age was 49 years. From series, 87% were invasive ductal carcinoma, 58% premenopausal, 50% grade III, 23% luminal , 39% basal and 38% HER2+. Ki67 was centrally assessed by IHC (MIB1 clone) and median score was 40% (range 1-100%). Pathological Complete Response (pCR), defined as absence of invasive cells in breast and lymph nodes, was achieved in 56 pts (29%). Univariate and multivariate logistic regression models were used to study the association of each clinical-pathological variable with pCR. ROC curves were used to determine the most accurate ki67 cut-off for predicting NC response. Results: Ki67≥50% was defined as the most accurate threshold to select patients obtaining benefit from NC. In the univariate analysis, histological grade (p=0.01), treatment (P=0.006), ER (p<0.0001), PR (p<0.0001), HER2 (p=0.01), and Ki67≥50% (p=0.0003) were statistically associated with pCR. A multivariate logistic regression showed that only Ki67≥ 50% (p=0.0003; OR=5.4 CI95% 2.1-13.4), ER (p=0.0001; OR=0.2 CI95% 0.1-0.4), and HER2 status (p<0.0001; OR=8.8 CI95% 3.3-23.6) were predictive for pCR (AUC=0.7812). Conclusions: These results suggest that a high proliferation in breast cancer measured by Ki67 marker is an independent predictive factor for pCR in an unclassified HER2 population of OBC patients treated with NC.

scholarly journals Role of Tumor Subtypes in Response to Neoadjuvant Chemotherapy in Non-metastatic Breast Cancer

2021 ◽  
Vol 24 (12) ◽  
pp. 881-886
Author(s):  
Negar Mashoori ◽  
Ramesh Omranipour ◽  
Abdolali Assarian
Keyword(s):  
Breast Cancer ◽  
Metastatic Breast Cancer ◽  
Neoadjuvant Chemotherapy ◽  
Pathologic Complete Response ◽  
Metastatic Breast ◽  
Tumor Grade ◽  
Her2 Status ◽  
Luminal A ◽  
Luminal B ◽  
Female Patients

Background: Neoadjuvant chemotherapy (NAC) is an integral part of breast cancer treatment. Determination of the factors that can distinguish patients who will have best response to NAC is invaluable. In this study, we aimed to elucidate the factors influencing patient response to NAC. Methods: We retrospectively collected data of female patients with non-metastatic breast cancer that had received NAC followed by surgery, admitted to Imam Khomeini hospital between 2015–2019. We investigated the association between various tumor and patients’ characteristics with pathologic complete response (PCR). Results: Overall data of 205 female patients were collected. PCR was observed in 27.6% of cases. PCR rate in luminal A, luminal B, HER2 enriched, and TNB tumors was reported in 11.1%, 30.2%, 35.7%, and 36.4% of patients respectively (P=0.27). In patients with luminal B tumors, PCR was more prevalent in patients with positive HER2 only (P=0.006). In our study factors which was significantly associated with PCR were: tumor grade, progesterone receptor (PR) status, and HER2 status. In the multiple regression model, positive PR in the tumor lowered the odds of pathologic response 3.6 times (P=0.004). Conclusion: In our study, tumor grade, PR status, and HER2 status was associated with response to NAC. PCR was more prevalent in non-luminal tumors; however, PCR rate in luminal B patients-especially those with HER2 positive status- was slightly less than non-luminals.

scholarly journals The Prognostic Impact of Body Composition for Locally Advanced Breast Cancer Patients Who Received Neoadjuvant Chemotherapy

Cancers ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 608
Author(s):  
Toshiaki Iwase ◽  
Aaroh Parikh ◽  
Seyedeh S. Dibaj ◽  
Yu Shen ◽  
Tushaar Vishal Shrimanker ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Body Composition ◽  
Adipose Tissue ◽  
Neoadjuvant Chemotherapy ◽  
Advanced Breast Cancer ◽  
Locally Advanced Breast Cancer ◽  
Locally Advanced ◽  
Pathologic Complete Response ◽  
Complete Response ◽  
Advanced Breast

Our previous study indicated that a high amount of visceral adipose tissue was associated with poor survival outcomes in patients with early breast cancer who received neoadjuvant chemotherapy. However, inconsistency was observed in the prognostic role of body composition in breast cancer treatment outcomes. In the present study, we aimed to validate our previous research by performing a comprehensive body composition analysis in patients with a standardized clinical background. We included 198 patients with stage III breast cancer who underwent neoadjuvant chemotherapy between January 2007 and June 2015. The impact of body composition on pathologic complete response and survival outcomes was determined. Body composition measurements had no significant effect on pathologic complete response. Survival analysis showed a low ratio of total visceral adipose tissue to subcutaneous adipose tissue (V/S ratio ≤ 34) was associated with shorter overall survival. A changepoint method determined that a V/S ratio cutoff of 34 maximized the difference in overall survival. Our study indicated the prognostic effect of body composition measurements in patients with locally advanced breast cancer compared to those with early breast cancer. Further investigation will be needed to clarify the biological mechanism underlying the association of V/S ratio with prognosis in locally advanced breast cancer.

scholarly journals Triple negative breast cancer subtypes and pathologic complete response rate to neoadjuvant chemotherapy

Oncotarget ◽  
2018 ◽  
Vol 9 (41) ◽  
pp. 26406-26416 ◽  
Author(s):  
Angela Santonja ◽  
Alfonso Sánchez-Muñoz ◽  
Ana Lluch ◽  
Maria Rosario Chica-Parrado ◽  
Joan Albanell ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neoadjuvant Chemotherapy ◽  
Triple Negative Breast Cancer ◽  
Triple Negative ◽  
Response Rate ◽  
Complete Response Rate ◽  
Pathologic Complete Response ◽  
Complete Response ◽  
Cancer Subtypes ◽  
Pathologic Complete Response Rate
Sign in / Sign up

Export Citation Format

Share Document